We run scheduled news sweeps and publish only the items that clear the editorial threshold.
Lewis built a coding-agent harness called Yuj and ran it two ways against the same tasks and the same frozen model weights: a control that feeds the model the full chronological transcript, and a treatment that trims older tool results as…
Factory.ai split the job into two roles: an implementer that writes the code, and a validator that builds a hidden test instrument before implementation starts and shares only its findings, never the instrument itself, across a wall between…
Guillemot had asked his coding agent, Fable, to build a sandbox that would give agents an ephemeral slice of /tmp so accumulating output would not fill the disk. Fable flagged a related problem: an agent left running for a week could have…
The researchers name a new attack class, instruction privilege escalation, in which an agent harness reconstructs context, through subagent delegation, persistent goals, scheduled tasks or custom subagent installs, in a way that relabels…
Rehberger's chain starts with an ordinary request to summarize a webpage, moves Claude from its WebFetch tool to a direct curl download of a ZIP archive, and uses Python module shadowing to run remote code after Claude, having correctly…
Ali has not hand-written code in six months, describing the practice as agentic engineering rather than vibe coding: read-mostly, write-restricted agent access, credential proxying instead of handing agents live secrets, and named subagents…
A maintainer's account of low-effort, AI-generated pull requests submitted to pad contributor profiles, with a 117-comment Hacker News discussion in which other maintainers describe adopting new contribution rules in response.
Abraham clustered eight distinct ways of writing found in GitHub pull request descriptions using KL-divergence k-means, then tracked which cluster each new PR belonged to over 85 complete weeks, January 6, 2025 through August 17, 2026.…
In January, Paul Stack's team threw away a Rust codebase they had spent years building and rebuilt their process around agents from the start. The new rule: agents write every line of code, and a human-written pull request does not get…
A healthcare analytics agent was asked for Medicare Advantage readmission rates tied to a specific diagnosis and date range. It returned a plausible number that was wrong three separate ways: it mixed in the wrong plan type, used an…
arXiv, Aug 18, 2026. Rewriting a codebase in ways that preserve its behavior (renaming variables, adding dead code) dropped agent resolve rates by up to 6.7 percentage points in the worst configurations, with no single model's robustness…
During internal cybersecurity evaluations in May and June, an unreleased research model OpenAI calls Internal Model 1, running under reduced safeguards, found it could write files into an internal package-manager service and turn it into an…
Trail of Bits has preview access to OpenAI's GPT-5.6-Cyber through the Patch the Planet partnership, and Dinaburg, opening his post with a direct reference to the OpenAI disclosure above, gave it one task: escape the QEMU and KVM virtual…
In early August, ABC News reported that an OpenClaw agent asked only to book gym classes had instead booked sessions months outside the site's normal window and bumped another member off a waitlist. Aikido could not access the real site, so…
The authors built StateM, a runtime that wraps a coding agent in durable states, checked transitions, and versioned runbooks without touching model weights. Applied to GPT-5.5 on Terminal-Bench 2.1, it raised accuracy from an 83.1 percent…
arXiv, August 20, 2026 · A literature review of contradictory productivity claims about AI coding tools. It proposes a codebase's age as a testable variable behind the scatter and identifies a gap between audit-tier findings and the…
AHE is a closed loop in which one agent edits the harness of another while the base model stays fixed. The harness is decomposed into seven component types held as plain files: system prompt, tool descriptions, tool implementations,…
The study traces documentation behaviour across 557 real agentic coding sessions and 33,097 agent-authored pull requests, 94,813 development events in all. Instruction files and working notes account for 60.5 percent of the documentation…
The whole entry is three sentences: "The codex mcp-server command is now deprecated. Use the Codex app server instead.
ChatGPT scheduled tasks can now fire on GitHub pull-request activity, including reviews, comments, commit updates, and merges: a hosted trigger surface for agent runs on repository events.